潜在几何和弦：面向查询高效决策型对抗攻击
Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks
AI总结：
提出潜在几何和弦（LGC）方法，通过曲率感知的几何搜索在压缩语义流形中导航决策边界，并引入残差对抗生成（RAG）机制以高视觉保真度实现查询高效的决策型黑盒对抗攻击。
摘要：
虽然基于决策的黑盒对抗攻击构成了严重的安全威胁，但当前方法存在根本性限制。像素级攻击经常引入不自然的高频视觉伪影，而潜在空间框架受限于低维流形的有限搜索空间和固有的重建缺陷。为解决这些限制，我们提出了潜在几何和弦（LGC）用于查询高效的决策型对抗攻击及其变体LGC-H。其核心是，LGC通过在压缩语义流形内执行曲率感知的几何搜索来导航决策边界。为保证高视觉保真度并规避维度瓶颈，我们引入了基于残差的对抗生成（RAG）机制。RAG将语义扰动隔离为几何和弦，并直接叠加到原始源图像上。RAG显著解决了基线重建缺陷，并有效将允许的搜索空间维度翻倍。实验结果表明，LGC实现了鲁棒的跨数据集迁移性，并显著优于最先进的基线方法。值得注意的是，我们的方法LGC在最小化扰动幅度的同时实现了最先进的视觉保真度——在5000次查询下结构相似性指数（SSIM）超过0.99，学习感知图像块相似度（LPIPS）低于0.01——并在严格的感知约束下保持高攻击成功率，成功攻破了经过对抗训练的鲁棒模型。源代码可在https://github.com/eihmuekhine/Latent-Geometric-Chords获取。
英文摘要：
While decision-based black-box adversarial attacks present a severe security threat, current methodologies suffer from fundamental limitations. Pixel-wise attacks frequently introduce unnatural, high-frequency visual artifacts, while latent-space frameworks are confined by the limited search space of low-dimensional manifolds and inherent reconstruction flaws. To resolve these limitations, we propose Latent Geometric Chords (LGC) for Query-Efficient Decision-Based Adversarial Attacks alongside a variant, LGC-H. At its core, LGC navigates decision boundaries by executing a curvature-aware geometric search within a compressed semantic manifold. To guarantee high visual fidelity and circumvent dimensionality bottlenecks, we introduce a Residual-based Adversarial Generation (RAG) mechanism. RAG isolates semantic perturbations as geometric chords and superimposes them directly onto the original source image. RAG substantially resolves baseline reconstruction flaws and effectively doubles the permissible search space dimensions. Experimental results demonstrate that LGC achieves robust cross-dataset transferability and substantially outperforms state-of-the-art baselines. Notably, our method, LGC, minimizes perturbation magnitudes while achieving state-of-the-art visual fidelity--with a Structural Similarity Index Measure (SSIM) exceeding 0.99 and a Learned Perceptual Image Patch Similarity (LPIPS) below 0.01 at 5000 queries--and sustaining high attack success rates under stringent perceptual constraints, successfully compromising adversarially trained robust models. The source code is available at: https://github.com/eihmuekhine/Latent-Geometric-Chords.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
